牛哥精选 · 所有

📋 全部 🤖 AI·大模型 ⚡ 效率工具 📝 深度技术 🚀 产品观察 💰 商业科技 🔓 开源项目 🎨 设计创意 📖 阅读推荐 🏷 资源合集 🌱 成长效率

🤖 AI·大模型 arXiv AI 2026-05-28

ReflexGrad: Within-Episode Failure Recovery in LLM Agents via Progress-Gated Dual-Process Routing

LLM智能体单次任务执行中自主容错新方案，进度门控双过程路由突破失败恢复瓶颈

arXiv:2511.14584v3 Announce Type: replace-cross Abstract: We present ReflexGrad, a dual-process architecture for within-episode failure recovery in LL…

llm agent 失败恢复双过程路由进度门控自主推理

📝 深度技术 arXiv AI 2026-05-27

Experiments in Agentic AI for Science

探索智能体AI在科学研究中的实验方法与前沿应用，揭示AI驱动科学发现的新路径。

arXiv:2605.26305v1 Announce Type: new Abstract: This paper details two novel frameworks for developing autonomous, agentic AI in scientific workflows.…

智能体 ai for sci 科学实验自主推理自动化发现

🤖 AI·大模型 arXiv 机器学习 2026-05-21

Towards Autonomous Mechanistic Reasoning in Virtual Cells

虚拟细胞自主推理新突破，让AI像科学家一样理解细胞机制。

arXiv:2604.11661v3 Announce Type: replace Abstract: Large language models (LLMs) have recently gained significant attention as a promising approach to…

虚拟细胞自主推理机制推理 ai科学计算大模型

📅 日期

2026-05-20 2026-05-19

🐂 牛哥精选

ReflexGrad: Within-Episode Failure Recovery in LLM Agents via Progress-Gated Dual-Process Routing

Experiments in Agentic AI for Science

Towards Autonomous Mechanistic Reasoning in Virtual Cells

📅 日期